[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WA4THHSEMGTGZH7KZ6WNH":3,"skill-same:01M78WA4THHSEMGTGZH7KZ6WNH":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78WA4THHSEMGTGZH7KZ6WNH","mjcf-mujoco-models",null,"Build, parse, compose, export, compile, step, inspect, and optionally render MJCF\u002FMuJoCo models with dm_control.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdm-control\u002Fsub-skills\u002Fmjcf-mujoco-models\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mjcf-mujoco-models\ndescription: \"Build, parse, compose, export, compile, step, inspect, and\n  optionally render MJCF\u002FMuJoCo models with dm_control.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# MJCF and MuJoCo Models\n\nUse this sub-skill when a task is about raw MJCF\u002FPyMJCF models or `dm_control.mujoco.Physics`: building XML object models, parsing model files or strings, composing attached models, exporting assets, compiling a `Physics`, stepping\u002Fresetting state, named data\u002Fmodel inspection, action specs, or a small render probe.\n\n## Route before working\n\n- Stay here for `dm_control.mjcf.RootElement`, `Element.add\u002Ffind\u002Ffind_all`, parser\u002Fexport helpers, `mjcf.Physics.from_mjcf_model`, `mujoco.Physics.from_xml_string\u002Ffrom_xml_path`, `physics.named`, `reset_context`, `mujoco.action_spec`, and `physics.render` API usage.\n- Route custom Composer `Entity`, `Task`, observable, and variation abstractions to [composer-environments](..\u002Fcomposer-environments\u002FSKILL.md).\n- Route Control Suite benchmark loading, wrappers, and rollout loops to [suite-rl-workflows](..\u002Fsuite-rl-workflows\u002FSKILL.md).\n- Route operational OpenGL, viewer, pixel-observation, EGL\u002FOSMesa\u002FGLFW, and Blender-exporter troubleshooting to [rendering-viewer-assets](..\u002Frendering-viewer-assets\u002FSKILL.md).\n\n## Installation and runtime guardrails\n\nInstall the public package with:\n\n```bash\npip install dm_control\n```\n\nFor unreleased source installs use:\n\n```bash\npip install git+https:\u002F\u002Fgithub.com\u002Fgoogle-deepmind\u002Fdm_control.git\n```\n\nEditable installs are not supported; do not rely on a source checkout, local paths, notebooks, or repository tests at runtime. Rendering is optional: CPU model construction, compile, reset, and stepping should work without an OpenGL backend, while `physics.render` depends on a configured MuJoCo GL backend.\n\n## Read or run these bundled files\n\n- Read [references\u002Fpymjcf-reference.md](references\u002Fpymjcf-reference.md) when creating, parsing, modifying, attaching, namespacing, validating, or exporting MJCF\u002FPyMJCF models.\n- Read [references\u002Fmujoco-physics-reference.md](references\u002Fmujoco-physics-reference.md) when compiling models into `Physics`, stepping\u002Fresetting simulations, using named data\u002Fmodel access, deriving action specs, rendering, or wrapping a custom `dm_env` environment.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when schema\u002Fattribute validation, duplicate names, invalid references, assets, compile failures, render backend selection, or simulation divergence blocks progress.\n- Run [scripts\u002Fmjcf_smoke_model.py](scripts\u002Fmjcf_smoke_model.py) to verify an installed `dm_control` can build a tiny PyMJCF model, compile `mjcf.Physics`, step it, optionally render, and optionally write the generated XML.\n\n## Default operating sequence\n\n1. Choose the level: PyMJCF object model for programmatic construction\u002Fcomposition; raw `mujoco.Physics` constructors for existing XML or MJB models.\n2. Build or parse the model; use `dclass` for XML `class`, `getattr(model.visual, 'global')` for keyword child names, and direct `mjcf.Element` references for reference attributes.\n3. If composing models, attach a fresh or copied child model, keep the returned attachment frame if joints\u002Finertials are needed, and validate namespaced identifiers after attachment.\n4. Compile with `mjcf.Physics.from_mjcf_model(model)` or `mujoco.Physics.from_xml_string(xml, assets=model.get_assets())` before claiming the model is valid.\n5. Inspect and control through `physics.named`, `physics.bind(element)` for PyMJCF elements, `reset_context`, `set_control`, `step`, and `mujoco.action_spec`.\n6. Treat rendering as an optional probe. If rendering fails but non-rendering compile\u002Fstep succeeds, preserve the model result and route backend diagnosis to the rendering sibling skill.\n","# MJCF and MuJoCo Models\n\nUse this sub-skill when a task is about raw MJCF\u002FPyMJCF models or `dm_control.mujoco.Physics`: building XML object models, parsing model files or strings, composing attached models, exporting assets, compiling a `Physics`, stepping\u002Fresetting state, named data\u002Fmodel inspection, action specs, or a small render probe.\n\n## Route before working\n\n- Stay here for `dm_control.mjcf.RootElement`, `Element.add\u002Ffind\u002Ffind_all`, parser\u002Fexport helpers, `mjcf.Physics.from_mjcf_model`, `mujoco.Physics.from_xml_string\u002Ffrom_xml_path`, `physics.named`, `reset_context`, `mujoco.action_spec`, and `physics.render` API usage.\n- Route custom Composer `Entity`, `Task`, observable, and variation abstractions to [composer-environments](..\u002Fcomposer-environments\u002FSKILL.md).\n- Route Control Suite benchmark loading, wrappers, and rollout loops to [suite-rl-workflows](..\u002Fsuite-rl-workflows\u002FSKILL.md).\n- Route operational OpenGL, viewer, pixel-observation, EGL\u002FOSMesa\u002FGLFW, and Blender-exporter troubleshooting to [rendering-viewer-assets](..\u002Frendering-viewer-assets\u002FSKILL.md).\n\n## Installation and runtime guardrails\n\nInstall the public package with:\n\n```bash\npip install dm_control\n```\n\nFor unreleased source installs use:\n\n```bash\npip install git+https:\u002F\u002Fgithub.com\u002Fgoogle-deepmind\u002Fdm_control.git\n```\n\nEditable installs are not supported; do not rely on a source checkout, local paths, notebooks, or repository tests at runtime. Rendering is optional: CPU model construction, compile, reset, and stepping should work without an OpenGL backend, while `physics.render` depends on a configured MuJoCo GL backend.\n\n## Read or run these bundled files\n\n- Read [references\u002Fpymjcf-reference.md](references\u002Fpymjcf-reference.md) when creating, parsing, modifying, attaching, namespacing, validating, or exporting MJCF\u002FPyMJCF models.\n- Read [references\u002Fmujoco-physics-reference.md](references\u002Fmujoco-physics-reference.md) when compiling models into `Physics`, stepping\u002Fresetting simulations, using named data\u002Fmodel access, deriving action specs, rendering, or wrapping a custom `dm_env` environment.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when schema\u002Fattribute validation, duplicate names, invalid references, assets, compile failures, render backend selection, or simulation divergence blocks progress.\n- Run [scripts\u002Fmjcf_smoke_model.py](scripts\u002Fmjcf_smoke_model.py) to verify an installed `dm_control` can build a tiny PyMJCF model, compile `mjcf.Physics`, step it, optionally render, and optionally write the generated XML.\n\n## Default operating sequence\n\n1. Choose the level: PyMJCF object model for programmatic construction\u002Fcomposition; raw `mujoco.Physics` constructors for existing XML or MJB models.\n2. Build or parse the model; use `dclass` for XML `class`, `getattr(model.visual, 'global')` for keyword child names, and direct `mjcf.Element` references for reference attributes.\n3. If composing models, attach a fresh or copied child model, keep the returned attachment frame if joints\u002Finertials are needed, and validate namespaced identifiers after attachment.\n4. Compile with `mjcf.Physics.from_mjcf_model(model)` or `mujoco.Physics.from_xml_string(xml, assets=model.get_assets())` before claiming the model is valid.\n5. Inspect and control through `physics.named`, `physics.bind(element)` for PyMJCF elements, `reset_context`, `set_control`, `step`, and `mujoco.action_spec`.\n6. Treat rendering as an optional probe. If rendering fails but non-rendering compile\u002Fstep succeeds, preserve the model result and route backend diagnosis to the rendering sibling skill.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fdm-control\u002Fsub-skills\u002Fmjcf-mujoco-models",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill mjcf-mujoco-models",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill mjcf-mujoco-models",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill mjcf-mujoco-models","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdm-control\u002Fsub-skills\u002Fmjcf-mujoco-models\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fmujoco-physics-reference.md","REFERENCE","参考文档",8612,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdm-control\u002Fsub-skills\u002Fmjcf-mujoco-models\u002Freferences\u002Fmujoco-physics-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fpymjcf-reference.md",10478,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdm-control\u002Fsub-skills\u002Fmjcf-mujoco-models\u002Freferences\u002Fpymjcf-reference.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",9019,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdm-control\u002Fsub-skills\u002Fmjcf-mujoco-models\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fmjcf_smoke_model.py","SCRIPT","脚本",7821,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdm-control\u002Fsub-skills\u002Fmjcf-mujoco-models\u002Fscripts\u002Fmjcf_smoke_model.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]